Contrastive Semantic-Guided Image Smoothing Network

09/02/2022
by   Jie Wang, et al.
2

Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details. Deep learning has been explored in image smoothing to deal with the complex entanglement of semantic structures and trivial details. However, current methods neglect two important facts in smoothing: 1) naive pixel-level regression supervised by the limited number of high-quality smoothing ground-truth could lead to domain shift and cause generalization problems towards real-world images; 2) texture appearance is closely related to object semantics, so that image smoothing requires awareness of semantic difference to apply adaptive smoothing strengths. To address these issues, we propose a novel Contrastive Semantic-Guided Image Smoothing Network (CSGIS-Net) that combines both contrastive prior and semantic prior to facilitate robust image smoothing. The supervision signal is augmented by leveraging undesired smoothing effects as negative teachers, and by incorporating segmentation tasks to encourage semantic distinctiveness. To realize the proposed network, we also enrich the original VOC dataset with texture enhancement and smoothing labels, namely VOC-smooth, which first bridges image smoothing and semantic segmentation. Extensive experiments demonstrate that the proposed CSGIS-Net outperforms state-of-the-art algorithms by a large margin. Code and dataset are available at https://github.com/wangjie6866/CSGIS-Net.

READ FULL TEXT

page 3

page 4

page 6

page 8

page 9

page 10

page 11

research
12/13/2021

Semantically Contrastive Learning for Low-light Image Enhancement

Low-light image enhancement (LLE) remains challenging due to the unfavor...
research
06/06/2019

Salient Building Outline Enhancement and Extraction Using Iterative L0 Smoothing and Line Enhancing

In this paper, our goal is salient building outline enhancement and extr...
research
12/07/2017

Deep Image Smoothing based on Texture and Structure Guidance

Image smoothing is a fundamental task in computer vision, which aims to ...
research
07/12/2023

Improved Real-time Image Smoothing with Weak Structures Preserved and High-contrast Details Removed

Image smoothing is by reducing pixel-wise gradients to smooth out detail...
research
11/07/2018

Image Smoothing via Unsupervised Learning

Image smoothing represents a fundamental component of many disparate com...
research
11/17/2021

SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining

Deep learning algorithms have recently achieved promising deraining perf...
research
10/27/2021

Robust Contrastive Learning Using Negative Samples with Diminished Semantics

Unsupervised learning has recently made exceptional progress because of ...

Please sign up or login with your details

Forgot password? Click here to reset